Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tomzx/agents --skill devils-advocategit clone --depth 1 https://github.com/tomzx/agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tomzx/agents/devils-advocate)<a href="https://agentmods.dev/skills/tomzx/agents/devils-advocate"><img src="https://agentmods.dev/badge/skills/tomzx/agents/devils-advocate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tomzx/agents/devils-advocate"><img src="https://agentmods.dev/badge/skills/tomzx/agents/devils-advocate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01718 |
| Opus 5.5 | $0.00029 | $0.00687 |
| Sonnet 5.5 | $0.00014 | $0.00344 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
devils-advocate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocate
Takes the user's position and constructs the strongest possible case against it, then surfaces assumptions, risks, blind spots, and alternatives the user may not have considered. The goal is not to win an argument but to find the weak points before they cause a problem. If the position survives serious challenge, the user proceeds with confidence; if it does not, they learn that now instead of later.
Prerequisites
- A position to challenge: an idea, plan, decision, proposal, argument, or course of action provided as an argument, in context, or via file paths.
- No codebase access required, though if the position involves code or architecture, read the relevant files to ground the challenge in reality rather than speculation.
How to Be a Useful Adversary
- Steel-man, do not straw-man. Construct the strongest version of the opposing view, not a weak one that is easy to knock down. The user benefits from the best counterarguments, not the easiest.
- Be specific, not generic. "This might fail" is useless; "this fails if the API rate limit is hit during peak hours because the retry logic has no backoff" is useful.
- Challenge the problem, not just the solution. Sometimes the idea is well-executed but solves the wrong problem. Flag that.
- Distinguish fatal flaws from manageable risks. Not every concern is a reason to stop. Be clear about severity.
- Stay constructive. The goal is to strengthen the user's thinking, not to paralyze them. End with a clear verdict and actionable next steps.
Steps
- Restate the user's position in your own words to confirm understanding. If the restatement does not match, ask for clarification before proceeding.
- Identify the core assumptions the position depends on. Mark each as explicit (stated by the user) or implicit (unstated but necessary).
- For each assumption, assess: how confident should the user be that it holds? What evidence supports it? What would disconfirm it?
- Construct the strongest counterargument. Argue against the position as if you genuinely believed the opposite, using the best available reasoning.
- Enumerate failure modes: what specifically goes wrong, under what conditions, and what the blast radius is.
- Identify blind spots: perspectives, stakeholders, or scenarios the user has not considered.
- Consider alternative paths: is there a meaningfully different way to achieve the same goal that the user dismissed or never considered?
- Trace second-order effects: what happens after the immediate outcome? What does this enable or block downstream?
- Assess opportunity cost and timing: is this the right thing to do now, or is there something more valuable being displaced?
- Deliver the verdict and recommendations using the output format below.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago Changed · +15 lines 9b4a87fa225f
- 23d ago Changed · -4 lines d29a9ca2666a
- 24d ago Changed 89a144a67b39
- 1mo ago First seen · 162 lines · 72 tokens per session scan A f0b00c71cefd
devils-advocate is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,718 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…